Titouan P
commited on
Commit
•
ae24638
1
Parent(s):
bace21d
configs
Browse files- config.json +77 -3
- preprocessor_config.json +8 -3
config.json
CHANGED
@@ -1,3 +1,77 @@
|
|
1 |
-
|
2 |
-
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"activation_dropout": 0.0,
|
3 |
+
"apply_spec_augment": true,
|
4 |
+
"architectures": [
|
5 |
+
"Wav2Vec2Model"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.1,
|
8 |
+
"bos_token_id": 1,
|
9 |
+
"conv_bias": false,
|
10 |
+
"conv_dim": [
|
11 |
+
512,
|
12 |
+
512,
|
13 |
+
512,
|
14 |
+
512,
|
15 |
+
512,
|
16 |
+
512,
|
17 |
+
512
|
18 |
+
],
|
19 |
+
"conv_kernel": [
|
20 |
+
10,
|
21 |
+
3,
|
22 |
+
3,
|
23 |
+
3,
|
24 |
+
3,
|
25 |
+
2,
|
26 |
+
2
|
27 |
+
],
|
28 |
+
"conv_stride": [
|
29 |
+
5,
|
30 |
+
2,
|
31 |
+
2,
|
32 |
+
2,
|
33 |
+
2,
|
34 |
+
2,
|
35 |
+
2
|
36 |
+
],
|
37 |
+
"ctc_loss_reduction": "sum",
|
38 |
+
"ctc_zero_infinity": false,
|
39 |
+
"do_stable_layer_norm": false,
|
40 |
+
"eos_token_id": 2,
|
41 |
+
"feat_extract_activation": "gelu",
|
42 |
+
"feat_extract_norm": "group",
|
43 |
+
"feat_proj_dropout": 0.1,
|
44 |
+
"final_dropout": 0.0,
|
45 |
+
"freeze_feat_extract_train": true,
|
46 |
+
"gradient_checkpointing": true,
|
47 |
+
"hidden_act": "gelu",
|
48 |
+
"hidden_dropout": 0.1,
|
49 |
+
"hidden_size": 768,
|
50 |
+
"initializer_range": 0.02,
|
51 |
+
"intermediate_size": 3072,
|
52 |
+
"layer_norm_eps": 1e-05,
|
53 |
+
"layerdrop": 0.05,
|
54 |
+
"mask_channel_length": 10,
|
55 |
+
"mask_channel_min_space": 1,
|
56 |
+
"mask_channel_other": 0.0,
|
57 |
+
"mask_channel_prob": 0.0,
|
58 |
+
"mask_channel_selection": "static",
|
59 |
+
"mask_feature_length": 10,
|
60 |
+
"mask_feature_prob": 0.0,
|
61 |
+
"mask_time_length": 10,
|
62 |
+
"mask_time_min_space": 1,
|
63 |
+
"mask_time_other": 0.0,
|
64 |
+
"mask_time_prob": 0.05,
|
65 |
+
"mask_time_selection": "static",
|
66 |
+
"model_type": "wav2vec2",
|
67 |
+
"no_mask_channel_overlap": false,
|
68 |
+
"no_mask_time_overlap": false,
|
69 |
+
"num_attention_heads": 12,
|
70 |
+
"num_conv_pos_embedding_groups": 16,
|
71 |
+
"num_conv_pos_embeddings": 128,
|
72 |
+
"num_feat_extract_layers": 7,
|
73 |
+
"num_hidden_layers": 12,
|
74 |
+
"pad_token_id": 0,
|
75 |
+
"transformers_version": "4.6.0.dev0",
|
76 |
+
"vocab_size": 32
|
77 |
+
}
|
preprocessor_config.json
CHANGED
@@ -1,3 +1,8 @@
|
|
1 |
-
|
2 |
-
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_normalize": false,
|
3 |
+
"feature_size": 1,
|
4 |
+
"padding_side": "right",
|
5 |
+
"padding_value": 0.0,
|
6 |
+
"return_attention_mask": true,
|
7 |
+
"sampling_rate": 16000
|
8 |
+
}
|